Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    own thoughts and personal narratives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Others
    0.94
    ्टी
    0.79
    another
    0.77
    One
    0.75
    Another
    0.74
    Only
    0.71
    For
    0.70
    Vacuum
    0.69
     anderer
    0.69
    Decrement
    0.68
    POSITIVE LOGITS
     volition
    1.23
     accord
    1.01
     stunts
    0.97
     backyard
    0.95
     unique
    0.94
     version
    0.93
     paltry
    0.92
     shortcomings
    0.91
     merits
    0.90
     penchant
    0.90
    Act Density 0.017%

    No Known Activations